← Plugin catalog
Data & Analytics

Statista

Statista GmbH v0.1.0

Market Research Data

Create a free account to save this plugin.

From the developer

Declared capabilities

  • Find statistics
  • Retrieve chart data
  • Compare markets across countries

Declared limitations

  • Reject an unsupported modification because the six research tools cannot edit Statista datasets.
  • Decline a request for identifiable survey records because Consumer Insights exposes aggregate results.
  • Request clarification before an underspecified market comparison.

Not specified in the available declarations: pricing & account requirements.

Onboarding example

Find Statista data for my research question and include the source links, dates, units, and relevant methodology.
Sources & dates

Developer declarations; not independently tested. Listing last checked Nov 22, 2026. Package observed Nov 21, 2026.

View package source →

Description

From the marketplace listing

The Statista Plugin provides ChatGPT with direct access to Statista’s comprehensive statistical database of over 80,000 topics from 50,000+ sources. This plugin enables real-time data discovery and retrieval from our extensive collection of charts, reports, and forecasts.

Language: English · Automatically detected from descriptions.

Changes

No changes recorded yet. Follow this plugin to keep track of future changes.

First seen Nov 18, 2026. Last seen Nov 22, 2026.

Similar plugins

Finding similar plugins… Results will appear here automatically.

Browse plugins →

Keywords

Files & skills

File archives

Plugin package19 files · 17.5 KBBrowse files →
Skill instructions
audience-profile5.54 KB

View saved version →

---
name: audience-profile
description: Profile a target consumer segment, covering who they are, what they value, how they behave in the category and what drives purchase, by indexing Statista Consumer Insights survey data against the general population. Use whenever someone asks to describe or understand a target audience, customer segment, persona, priority target or "who buys X", or wants consumer insight to brief a campaign, product or proposition, even without the word "segment".
---

# Audience Profile

Describe a segment by how it differs from the average consumer, not only by what it looks like. A trait counts as defining when it is common in the segment, over-represented against the population, and statistically significant.

**Scope:** demographics, values and interests, category behaviour, purchase drivers and barriers. Media consumption and brand metrics are out of scope.

## Inputs

| Input | Default if missing |
|---|---|
| Segment definition | Required. Ask if absent. |
| Country | The country named in the request; otherwise ask. |
| Survey year | Latest available |
| Comparison base | Online population aged 18–64 in that country's survey |

## How the Consumer Insights tools behave

- **Splits.** Survey questions sit in splits, shown as `splits_by_project_group` in search results. A segment can only be crossed with questions in the same split (e.g. `gcs: "2"`) or with demographic questions (`demo`). Any other combination returns a 404, and so does a country that never fielded the question. Report both as gaps.
- **Segment and total.** Crosstabs do not return a total column. Fetch each descriptor twice:
  - with `filters` = [defining answer ID] → segment %;
  - without filters → total %.
- **Single numbers.** An answer ID passed as `rows` returns one share for the country. Use it to read segment size.
- **Respondent counts.** Every cell carries one. The segment base is the count on the defining answer.

## Workflow

1. **Make the segment measurable.**
   - Call `search-consumer-insights` with short queries to find an answer that defines the segment, e.g. a shopper typology or "bought X in the last 12 months". Prefer answers in the core survey (`gcs`), because they cross with the most descriptors.
   - Fetch the defining answer as `rows` for the country to get the segment share and n.
   - If no answer fits, use the closest proxy and state the gap.
2. **Choose descriptors.** Pick 2–5 questions per block. Each must sit in the defining answer's split or be demographic.
   - **Demographics:** age, gender, household income for that country, community type.
   - **Values and interests:** life values, hobbies.
   - **Category behaviour:** online and offline purchases by category, premium purchase by category, channel.
   - **Drivers and barriers:** purchase criteria and reasons. These are often in other splits. Try them, and report a gap if they cannot be crossed.
3. **Fetch** segment % and total % for each descriptor, as above. Record each row's n. Mark rows as modelled when the description says data was filled from demographics.
4. **Index** every row as set out in "Indexing" below. Present only rows flagged distinctive as traits.
5. **Synthesize.**
   - **Defining traits:** 3–5, taken from the distinctive rows with the largest gaps.
   - **Portrait:** a plain-language description that claims nothing beyond the data.
   - **Implications:** for messaging, proposition and purchase channel, each tied to a row.
   - **Non-differentiators:** state traits that do not set the segment apart, e.g. "not younger than average". They prevent mis-targeting.

## Indexing

Collapse fine answer bands, such as income brackets, into 3–4 groups first. For each row, with segment % s, total % t and segment base n:

- **Index** = s ÷ t × 100.
- **z** = (s − t) ÷ √(t × (100 − t) ÷ n), with s and t in percent. Leave z blank when n is unknown or t is 0 or 100.
- **Flag**, taking the first that applies:
  - **distinctive:** index ≥ 120 or ≤ 8

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 1 — file references are metadata, not package contents.

growth-vs-market-check2.98 KB

View saved version →

---
name: growth-vs-market-check
description: Compares a company's actual or forecast revenue growth by segment and country with the growth of the corresponding external market, computes the gap in percentage points and the implied market-share change, flags forecasts that outrun their market, and drafts commentary for forecast reviews and monthly reports. Use whenever a user asks "are we growing faster than the market", needs market context for variance commentary, wants to sanity-check a budget or forecast against market growth, or provides revenue by segment and asks how it compares externally.
---

# Growth-vs-Market Check

## Purpose

Add an external driver to forecast review and monthly reporting. A forecast that outgrows its market for several years is the most common sign of over-optimism. The check turns it into a question for the unit owner, not a verdict.

## Inputs

| Input | Required | Default |
| --- | --- | --- |
| Internal revenue CSV: `segment,country,year,revenue,type` with type `actual` or `forecast` | Yes | — |
| Mapping of internal segments to market segments | No | Proposed by the skill, confirmed by the user |
| Flag thresholds | No | Gap above +5 points in a forecast year; gap above +3 points in three consecutive years ending in a forecast year |
| Currency basis (reported or constant) | No | Reported |

## Workflow

1. Validate the internal file: list the segment-country pairs and years, and confirm each pair has at least two consecutive years.
2. Propose a mapping from each internal segment to a market segment available in the data connector, with a confidence of exact, close or loose. Show the mapping table and wait for confirmation; taxonomy mismatch is the main cause of a wrong conclusion.
3. For each confirmed pair, fetch the market revenue series for the same years. Save all pairs in one CSV with columns `segment,country,year,market_revenue`, using the internal segment names.
4. Run `scripts/growth_gap.py --internal <internal.csv> --market <market.csv>`; pass `--gap-threshold`, `--run-gap` or `--run-years` when the user changed the defaults.
5. Write the commentary: one line per unflagged pair. For each flagged pair, write a short paragraph with the gap, the implied share change and the question for the owner, such as which initiatives or pricing actions support growth above the market.

## Output format

```
# Growth versus market: <scope>, <period>

## Mapping used
| Internal segment | Market segment | Confidence |

## Results
Table from growth_gap.py.

## Commentary

## Caveats
Mapping confidence, currency basis, source and release date of each market series.
```

## Data rules

- A share computed against a market estimate is itself an estimate; say so where it is quoted.
- Compare like with like: growth in reported currency includes exchange-rate effects the market series may not.
- A flag on a loosely mapped row means fix the mapping first.
- The internal file stays with the user; the skill reads it for the run and reproduces it only in the results table.

Referenced files: 2 — file references are metadata, not package contents.

market-sizing6.41 KB

View saved version →

---
name: market-sizing
description: Size a market as TAM, SAM and SOM with base, upside and downside forecasts, using Statista Market Insights and Statistics. Use whenever someone asks how big a market is, what a category is worth, the revenue opportunity for a launch or expansion, market potential, CAGR to a future year, or needs market numbers for a business case, annual plan or long-range plan, even if they never say "TAM".
---

# Market Sizing

Estimate what a market is worth today and at a horizon year, then narrow it to what the brand can realistically capture. Every number traces to a Statista source or to an assumption labelled as one.

## Inputs

Settle these before fetching anything. If one is missing, pick the default, state it in the output and continue.

| Input | Default |
|---|---|
| Market definition: products in and out of scope | The closest Statista Market Insights market |
| Geography | The country named in the request |
| Base year and horizon year | The latest year before the current one; base year + 5 || Brand | None. Without a brand, stop at SAM. |
| Serviceable filters: channels, sub-types, price tiers | None, so SAM = TAM |
| Obtainable share | The brand's current share; otherwise a benchmark from comparable brands |

## How the Statista tools behave

- `search-market-insights` returns one dataset per metric: revenue, volume, price per unit, growth and so on. Search on the category alone, without the country. Then pass country codes taken from that result's `covered_geos` to `fetch-market-insights`, at most five per call.
- Each dataset has a `market_type`.
  - **Consumer:** the whole market, all channels. Use this for TAM.
  - **eCommerce:** the online channel only. User counts, ARPU and penetration usually come only as eCommerce datasets, so a TAM built from users × ARPU measures the online channel, not the market.
- Market Insights revenue comes in USD. Volume × price per unit reproduces revenue exactly, so it is an internal identity and does not count as a cross-check.
- `search-statistics` also returns charts derived from Market Insights. Their `sources` field names "Statista Market Insights". Charts like these are not independent and cannot be used for triangulation.
- The brand-profile charts from `search-statistics` give each brand's awareness, usage and loyalty among category users. Usage share is a proxy for value share, not equal to it.

## Workflow

1. **Define the market in one sentence**, including what it excludes. Unclear definitions are the main cause of wrong sizes.
2. **Pull the TAM.** Use the Consumer revenue dataset from `fetch-market-insights`, covering actual and forecast years. Record the unit, the forecast vintage (the dataset `id` prefix carries its release date) and the statista.com link. Note any gap between the Statista definition and the user's.
3. **Triangulate.** Find one estimate that does not come from Market Insights, using `search-statistics` then `get-chart-data-by-id`. Retail panel data, industry associations and trade press all count. Convert it to the TAM's currency and record the rate. A gap over 20% must be explained (definition, channel coverage, year) before you go further.
4. **Narrow to SAM.** Apply each serviceable filter as a share of the TAM, such as a sub-type's share of volume or the online share of revenue. Use a sourced share wherever one exists. Label any share older than three years as stale, and any share without a source as judgement.
5. **Estimate SOM.** Apply the obtainable share to the SAM. Anchor it to the brand's current share, or to usage shares of comparable brands from brand-profile charts. Never present a SOM without its share assumption.
6. **Build the scenarios.**
   - **Base:** Statista's forecast, using the CAGR implied by the series (see below).
   - **Upside and downside:** an adjusted CAGR and share for each, every adjustment tied to a named driver with one line of evidence. Growth-rate and volume-change charts are good evidence

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 1 — file references are metadata, not package contents.

statista-competitive-landscape2.3 KB

View saved version →

---
name: statista-competitive-landscape
description: Analyses competitors from Statista data covering market share, concentration, share momentum and brand standing. Use for competitor analysis, market share, brand health comparisons, positioning and single-competitor profiles.
---

# Statista Competitive Landscape

## Data

- Figures only from fetch calls (`fetch-market-insights`, `fetch-consumer-insights`, `get-chart-data-by-id`). Search returns IDs, not values. Statista only: no web, no model knowledge.
- IDs and geography codes exactly as returned. Reuse figures already fetched in this conversation.
- Cite bucket and year per figure. Label calculated figures with their inputs.

## Method

1. Fix the peer set before retrieving: category, geography, segment, period. No players added after seeing the data.
2. Share of market from one consistent share series. CR3/CR5 from that series, "other" kept.
3. Share of mind from one named brand metric: awareness, consideration, usage, loyalty.
4. Index both to the peer-set mean = 100. High share + low mind = vulnerable incumbent. Low share + high mind = emerging challenger.
5. Read movement where ≥2 periods exist. Rising consideration with flat share signals a challenger. One share vintage only: report structure, not momentum; list multi-period share as an open item.

## Inputs

| Input | Bucket |
|---|---|
| Market share, revenue by company, category revenue | Market Insights |
| Single-company revenue, number of players | Statistics |
| Awareness, consideration, usage, loyalty | Consumer Insights |

No share data: a brand landscape, not a ranking. No brand data: share and structure only.

## Single competitor

Share and movement, revenue trend, brand funnel vs peer mean, segments where it over- or under-indexes. Strategy, products and partnerships are not in Statista: list as open items.

## Exhibits

Show who leads and how concentrated the market is, how share compares with brand standing, and how positions moved. Chart only when the reader needs a shape.

## Output

1. Headline: who holds power, how it is moving
2. Share and concentration
3. Share vs brand standing
4. Who is exposed, who is emerging
5. Implication for entry, defence or positioning

## Gotchas

- Shares from different market definitions cannot be ranked together.
- Awareness is not demand or loyalty.

Referenced files: 1 — file references are metadata, not package contents.

statista-data2.75 KB

View saved version →

---
name: statista-data
description: Retrieves and answers with Statista figures from Market Insights, Consumer Insights and Statistics. Use for a single figure, a lookup, a trend, a quick comparison, or whether Statista covers a topic. Not for sizing, scoring, frameworks or decks.
---

# Statista Data

## Route

| Need | Bucket | Tools |
|---|---|---|
| Market size, revenue, forecast, CAGR, ARPU, share | Market Insights | `search-market-insights` → `fetch-market-insights` |
| Intent, WTP, brand, channel, buyer demographics | Consumer Insights | `search-consumer-insights` → `fetch-consumer-insights` |
| Counts, actual spend, adoption, single companies, niche series | Statistics | `search-statistics` → `get-chart-data-by-id` |

Out of scope: live prices, M&A, funding, valuations, ownership, regulation, company filings. Ecommerce connector tools (`search-ecommerce`, `ranked-ecommerce`, `metrics-ecommerce`, `profile-ecommerce`, `shopper-ecommerce`) are out of scope until documented. Say so and name the closest Statista coverage.

## Retrieve

- Run all searches in one parallel batch, then fetch in one batch. Searches are cheap, fetches are the budget.
- Search returns IDs and metadata, never values. Ignore numbers in search titles and descriptions. Every figure comes from a fetch.
- Market Insights `geo`: at most 5 codes per `fetch-market-insights` call; split into batches if more are needed.
- Nothing relevant found: stop, say what was searched, offer a narrower or adjacent angle.
- Statista only. No web, no model knowledge, no estimates.

## Gotchas

- Market Insights geography codes come from `covered_geos` in search results. Pass them exactly (`DEU`, not `Germany`). A missing country is not covered. Fetch several geos in one call.
- Regional codes are aggregates, never sums of countries.
- Market Insights growth rates are decimals (0.10 = 10%).
- Consumer Insights search is keyword-based: 2–3 words. Crosstabs need both variables from the same survey and country. Skip year-named variables (`..._2023`). Thin cells are not findings.
- `search-statistics` returns a `link`: keep it as the source URL. Never build a URL.
- Use the newest vintage per metric. Never mix vintages in one comparison; flag data older than two years.
- Reuse figures already fetched in this conversation.

## Cross-check

When two buckets cover the same quantity: spread = |A − B| / mean. ≤30% triangulated, 30–67% report both, >67% direction only. Never average. Single source = Low or Medium confidence.

## Answer

Answer first, with the number, year and confidence. Cite bucket and year per figure. Label calculated figures with their inputs. State currency, and actual vs forecast. Chart only when the reader needs a shape (trend of 3+ points, ranking of 4+); otherwise a sentence or table.

Referenced files: 1 — file references are metadata, not package contents.

trend-radar4.32 KB

View saved version →

---
name: trend-radar
description: Find, measure and grade consumer and category trends with Statista Consumer Insights, Market Insights and Statistics, separating established shifts from emerging ones, weak signals and hype. Use whenever someone asks what the trends are in a category, for a trend report or trend scan, whether something is a fad, what to bet on for innovation or content, or which consumer shifts matter for next year's plan.
---

# Trend Radar

A trend is a change over time; a single data point is not one. This skill turns a topic into a short list of candidate shifts, measures each one over time against its parent category, and grades how strongly the data supports it.

## Inputs

| Input | Default if missing |
|---|---|
| Topic or category | Required. Ask if absent. |
| Markets | The country or countries named in the request |
| Look-back window | The last 3–7 years of actual data |
| Candidate trends | Generated in step 2, plus any the user names |

## Workflow

1. **Frame the topic** as a category plus a consumer need, e.g. "food & drink × health". This keeps the candidates relevant.
2. **Generate 6–10 candidates**, each named as a shift ("from X to Y") with a one-line definition. Draw them from three sources:
   - **Market Insights segments.** Look for segments whose revenue grows faster than their parent category. `search-statistics` returns compact single-country versions of these series. Their descriptions already state the latest value, the forecast and the change in growth, so they save fetch calls.
   - **Consumer Insights.** Look for questions that track a behaviour or diet over years. Call `fetch-consumer-insights` once per year with `year` set. Then read the "Changes in wording and/or filtering" note in the description: a wording change breaks the series.
   - **Independent statistics.** Use national statistics offices, panels or industry bodies (found with `search-statistics`) for adoption, production or sales series.
3. **Measure each candidate.** For each one record:
   - its level (share of consumers or share of the parent category's revenue);
   - its momentum (pp change, or CAGR compared with the parent category's CAGR);
   - how many independent sources agree;
   - its commercial pull;
   - the number of years in the series;
   - the latest and average yearly change.

   When two or more markets are in scope, also count the markets moving the same way.
4. **Grade** each candidate with `references/evidence-grading.md`: assign Established, Emerging, Weak signal or Not supported, and a direction. Apply the thresholds exactly. A measure you did not take counts as missing, never as passing. Check every Not supported trend: these results often make the most useful headline.
5. **Set watch indicators.** For each Emerging trend and Weak signal, name the metric and the threshold that would upgrade or retire it.

Before grading, make sure every candidate has a level. A missing level cannot reach Established or Emerging, so a well-supported trend with no level recorded will be under-graded. If the trend's own share is unavailable, use a proxy level as described in the reference file.

## Output

1. **Summary:** three sentences. Say which shifts are real, which are early, and which popular claims the data does not support.
2. **Radar table**, sorted by grade (Established first):

   | Trend | Grade | Direction | Level | Momentum | Corroboration | Pull | Years |
   |---|---|---|---|---|---|---|---|

   Level reads "x% consumers" or "x% revenue" (mark proxies). Momentum reads "+x.x pp" or "CAGR x.x% vs category y.y%". Every metric carries its years, market and source.
3. **Implications:** one line per Established or Emerging trend, aimed at product, proposition or content.
4. **Not supported:** the expected or hyped trends the data does not support, and why.
5. **Watch list:** indicator, current value and trigger threshold.
6. **Sources:** statistic IDs, Market Insights dataset IDs and Consumer Insights 

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 2 — file references are metadata, not package contents.

Release notes

Initial release of the Statista plugin with OAuth sign-in, statistical search and chart retrieval, Market Insights comparisons, and Consumer Insights survey analysis. Includes competitive landscape, Statista data lookup, growth-versus-market checks, audience profiling, market sizing, and trend radar skills.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
Adam Ingwersen
Keywords
See keywords
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Find statistics
  • Retrieve chart data
  • Compare markets across countries
  • Explore consumer survey results
  • Analyze consumer demographics

Package observed Nov 21, 2026.

Technical details
First seen
Nov 18, 2026 · 12:00 UTC
Last seen
Nov 22, 2026 · 00:00 UTC
Collection status
Collected

plugin_asdk_app_6af4843aed908191af6dcaf48b127b34

Download plugin data (JSON)

Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.